Johannes Rausch

Johannes Rausch is a senior deep learning engineer at NVIDIA within the Deep Learning Algorithms group, researching and developing methods for optimizing LLM efficiency. Before joining NVIDIA, he completed his PhD in Computer Science at ETH Zurich, focusing on building end-to-end machine learning systems for hierarchical document parsing.
Avatar photo

Posts by Johannes Rausch

Three icons, with text LLMs, Optimize, Deploy.
Generative AI

Dynamic Memory Compression

Despite the success of large language models (LLMs) as general-purpose AI tools, their high demand for computational resources make their deployment challenging... 9 MIN READ